Qwen3 235B-A22B
alibaba/qwen3-235b-a22b · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.22
Blended $/1M (3:1)
$0.7
Input $/1M
$2.8
Output $/1M
$3.50
1M in + 1M out
—
Cache read $/1M
#4392 of 7,708
Cheapest rank
- Provider
- Alibaba (
alibaba) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 16,384 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Qwen3 235B-A22B” is offered by 5 providers — cheapest-effective first. Hugging Face is the cheapest at $0.35 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Hugging Face | $0.2 | $0.8 | $0.35 | 41k |
| Alibaba (China) | $0.287 | $1.15 | $0.50 | 131k |
| Kilo Gateway | $0.455 | $1.82 | $0.80 | 131k |
| OpenRouter | $0.455 | $1.82 | $0.80 | 131k |
| Alibaba (this) | $0.7 | $2.8 | $1.22 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Alibaba and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen3-235b-a22b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):